Virtual Multi-view Fusion for 3D Semantic Segmentation

TL;DR

This paper introduces a virtual multiview fusion technique that enhances 3D mesh semantic segmentation by effectively combining 2D predictions from multiple views, outperforming previous multiview methods and rivaling 3D convolution approaches.

Contribution

The paper presents a novel virtual multiview fusion approach that improves 3D semantic segmentation accuracy by better leveraging 2D view-based predictions on 3D meshes.

Findings

Outperforms previous multiview methods on ScanNet benchmark.

Achieves results comparable to recent 3D convolution techniques.

Effectively integrates 2D predictions for improved 3D segmentation.

Abstract

Semantic segmentation of 3D meshes is an important problem for 3D scene understanding. In this paper we revisit the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes. Given a 3D mesh reconstructed from RGBD sensors, our method effectively chooses different virtual views of the 3D mesh and renders multiple 2D channels for training an effective 2D semantic segmentation model. Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels. Using the large scale indoor 3D semantic segmentation benchmark of ScanNet, we show that our virtual views enable more effective training of 2D semantic segmentation networks than previous multiview approaches. When the 2D per pixel predictions are aggregated on 3D surfaces, our virtual multiview fusion method is able to achieve significantly better 3D semantic segmentation results compared to all prior multiview approaches and competitive with recent 3D convolution approaches.